检索结果-内蒙古大学图书馆

Learning Transferable Negative Prompts for Out-of-Distribution Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Tianqi Pang, Guansong Bai, Xiao Miao, Wenjun Zheng, Jin School of Computer Science and Engineering State Key Laboratory of Complex & Critical Software Environment Jiangxi Research Institute Beihang University China School of Computing and Information Systems Singapore Management University Singapore

Existing prompt learning methods have shown certain capabilities in Out-of-Distribution (OOD) detection, but the lack of OOD images in the target dataset in their training can lead to mismatches between OOD images and In-Distribution (ID) categories, resulting in a high false positive rate. To address this issue, we introduce a novel OOD detection method, named ‘NegPrompt’, to learn a set of negative prompts, each representing a negative connotation of a given class label, for delineating the boundaries between ID and OOD images. It learns such negative prompts with ID data only, without any reliance on external outlier data. Further, current methods assume the availability of samples of all ID classes, rendering them ineffective in open-vocabulary learning scenarios where the inference stage can contain novel ID classes not present during training. In contrast, our learned negative prompts are transferable to novel class labels. Experiments on various ImageNet benchmarks show that NegPrompt surpasses state-of-the-art prompt-learning-based OOD detection methods and maintains a consistent lead in hard OOD detection in closed- and open-vocabulary classification scenarios. Code is available at https://***/mala-lab/negprompt. © 2024, CC BY.

关键词： Chemical detection

LECF: recommendation via learnable edge collaborative filtering

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2022年第1期65卷 116-130页

作者： Shitao XIAO Yingxia SHAO Yawen LI Hongzhi YIN Yanyan SHEN Bin CUI School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing Key Lab of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunications School of Information Technology and Electrical Engineering The University of Queensland Department of Computer Science and Engineering Shanghai Jiao Tong University Department of Computer Science and Technology Peking University National Engineering Laboratory for Big Data Analysis and Applications Peking University

The core of recommendation models is estimating the probability that a user will like an item based on historical interactions. Existing collaborative filtering(CF) algorithms compute the likelihood by utilizing simple relationships between objects, e.g., user-item, item-item, or user-user. They always rely on a single type of object-object relationship, ignoring other useful relationship information in data. In this paper, we model an interaction between user and item as an edge and propose a novel CF framework, called learnable edge collaborative filtering(LECF). LECF predicts the existence probability of an edge based on the connections among edges and is able to capture the complex relationship in data. Specifically, we first adopt the concept of line graph where each node represents an interaction edge; then calculate a weighted sum of similarity between the query edge and the observed edges(i.e., historical interactions) that are selected from the neighborhood of query edge in the line graph for a recommendation. In addition, we design an efficient propagation algorithm to speed up the training and inference of LECF. Extensive experiments on four public datasets demonstrate LECF can achieve better performance than the state-of-the-art methods.

关键词： collaborative filtering recommender system implicit feedback edge-edge similarity line graph

Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Zi-Hao Fang, Siyuan Zhou, Zi-Jing Wei, Tong Wan, Yuanyu Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China Xiaomi Inc. China School of Software Technology Zhejiang University Ningbo China

Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-quality pseudo-labels for large-scale unlabeled data. However, these methods often neglect the impact of representations learned by the neural network and struggle with real-world unlabeled data, which typically follows a different distribution than labeled data. This paper introduces a novel probabilistic framework that unifies various recent proposals in long-tail learning. Our framework derives the class-balanced contrastive loss through Gaussian kernel density estimation. We introduce a continuous contrastive learning method, CCL, extending our framework to unlabeled data using reliable and smoothed pseudo-labels. By progressively estimating the underlying label distribution and optimizing its alignment with model predictions, we tackle the diverse distribution of unlabeled data in real-world scenarios. Extensive experiments across multiple datasets with varying unlabeled data distributions demonstrate that CCL consistently outperforms prior state-of-the-art methods, achieving over 4% improvement on the ImageNet-127 dataset. Our source code is available at https://***/zhouzihao11/CCL. © 2024, CC BY.

关键词： Contrastive Learning

Research on Quality Model for Quantum Simulator software

学校读者我要写书评

暂无评论

Research on Quality Model for Quantum Simulator Software

software engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD-Winter), ACIS International Winter Conference on

作者： Chao Wang Jingwei Chen JianXin Ge XueZhong Wu QianQian Qu Le Luo Shanghai Key Laboratory of Computer Software Testing and Evaluating Shanghai Development Center of Computer Software Technology Shanghai China QUDOOR Technologies Inc. Hefei China Software Engineering of Computer and Information Engineering College Shanghai Polytechnic University Shanghai China QUDOOR Technologies Inc. School of Physics and Astronomy Sun Yat-Sen University Zhuhai China

In recent years, the demand for arithmetic power from all walks of life is growing, especially the increasing popularity of AIGC, which makes people realize that huge technological progress cannot be made without the support of large arithmetic power. Quantum computing may bring a leap in computing power and become a ”trigger” and “catalyst” to accelerate the development of science and technology innovation, and its technical development trend and application prospects have become a hot issue of concern, and quantum simulators are a very important part of the development process. The development of quantum simulators is a very important part of the process. However, due to the lack of systematic evaluation theories and methods, it is difficult to quantify and analyze the quality of the increasing number of simulators on the market, which may hinder researchers from practicing their quantum algorithms objectively or developing quantum technologies. For these reasons, this paper proposes a quality model for quantum simulator software, which reflects the quality characteristics of simulators in seven aspects, such as functionality and performance efficiency, and selects some simulators for experimental validation of the proposed model to prove its rationality.

关键词：

Joint DNN Partition and Thread Allocation Optimization for Energy-Harvesting MEC Systems

学校读者我要写书评

暂无评论

Joint DNN Partition and Thread Allocation Optimization for E...

Design, Automation and Test in Europe Conference and Exhibition

作者： Yizhou Shi Liying Li Yue Zeng Peijin Cong Junlong Zhou School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China National Mobile Communications Research Laboratory Southeast University Nanjing China Key Laboratory of Embedded System and Service Computing (Tongji University) Ministry of Education Shanghai China

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

Deep neural networks (DNNs) have demonstrated exceptional performance, leading to diverse applications across various mobile devices (MDs). Considering factors like portability and environmental sustainability, an increasing number of MDs are adopting energy harvesting (EH) techniques for power supply. However, the computational intensity of DNNs presents significant challenges for their deployment on these resource-constrained devices. Existing approaches often employ DNN partition or offloading to mitigate the time and energy consumption associated with running DNNs on MDs. Nonetheless, existing methods frequently fall short in accurately modeling the execution time of DNNs, and do not consider to use thread allocation for further latency and energy consumption optimization. To solve these problems, we propose a dynamic DNN partition and thread allocation method to optimize the latency and energy consumption of running DNNs on EH-enabled MDs. Specifically, we first investigate the relationship between DNN inference latency and allocated threads and establish an accurate DNN latency prediction model. Based on the prediction model, a DRL-based DNN partition (DDP) algorithm is designed to find the optimal partitions for DNNs. A thread allocation (TA) algorithm is proposed to reduce the inference latency. Experimental results from our test-bed platform demonstrate that compared to four benchmarking methods, our scheme can reduce DNN inference latency and energy consumption by up to 37.3% and 38.5%.

关键词： Energy consumption Instruction sets Heuristic algorithms Artificial neural networks Predictive models Prediction algorithms Inference algorithms Partitioning algorithms Resource management Optimization

Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jiang-Xin, Shi Tong, Wei Zhi, Zhou Jie-Jing, Shao Xin-Yan, Han Yu-Feng, Li National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China School of Computer Science and Engineering Southeast University China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China

The fine-tuning paradigm in addressing long-tail learning tasks has sparked significant interest since the emergence of foundation models. Nonetheless, how fine-tuning impacts performance in long-tail learning was not explicitly quantified. In this paper, we disclose that heavy fine-tuning may even lead to non-negligible performance deterioration on tail classes, and lightweight fine-tuning is more effective. The reason is attributed to inconsistent class conditions caused by heavy fine-tuning. With the observation above, we develop a low-complexity and accurate long-tail learning algorithms LIFT with the goal of facilitating fast prediction and compact models by adaptive lightweight fine-tuning. Experiments clearly verify that both the training time and the learned parameters are significantly reduced with more accurate predictive performance compared with state-of-the-art approaches. The implementation code is available at https://***/shijxcs/LIFT. Copyright © 2023, The Authors. All rights reserved.

关键词： Learning algorithms

Generalizing 6-DoF Grasp Detection via Domain Prior Knowledge

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Haoxiang Shi, Modi Gao, Boyang Huang, Di State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Computer Science and Technology Harbin Institute of Technology Harbin China Geometry Robotics China

We focus on the generalization ability of the 6-DoF grasp detection method in this paper. While learning-based grasp detection methods can predict grasp poses for unseen objects using the grasp distribution learned from the training set, they often exhibit a significant performance drop when encountering objects with diverse shapes and structures. To enhance the grasp detection methods’ generalization ability, we incorporate domain prior knowledge of robotic grasping, enabling better adaptation to objects with significant shape and structure differences. More specifically, we employ the physical constraint regularization during the training phase to guide the model towards predicting grasps that comply with the physical rule on grasping. For the unstable grasp poses predicted on novel objects, we design a contact-score joint optimization using the projection contact map to refine these poses in cluttered scenarios. Extensive experiments conducted on the GraspNet-1billion benchmark demonstrate a substantial performance gain on the novel object set and the real-world grasping experiments also demonstrate the effectiveness of our generalizing 6-DoF grasp detection method. Code is available at https://***/mahaoxiang822/ Generalizing-Grasp. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

A TMA-Seq2seq Network for Multi-Factor Time Series Sea Surface Temperature Prediction

学校读者我要写书评

暂无评论

computers, Materials & Continua 2022年第10期73卷 51-67页

作者： Qi He Wenlong Li Zengzhou Hao Guohua Liu Dongmei Huang Wei Song Huifang Xu Fayez Alqahtani Jeong-Uk Kim Department of Information Technology Shanghai Ocean UniversityShanghai201306China State Key Laboratory of Satellite Ocean Environment Dynamics Second Institute of OceanographyMinistry of Natural ResourcesHangzhou310012China College of Computer Dong Hua UniversityShanghai200051China College of Information Technology Shanghai Jian Qiao UniversityShanghai201306China Software Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh 12372Saudi Arabia Department of Electrical Engineering Sangmyung UniversitySouth KoreaKorea

Sea surface temperature (SST) is closely related to global climatechange, ocean ecosystem, and ocean disaster. Accurate prediction of SST isan urgent and challenging task. With a vast amount of ocean monitoring dataare continually collected, data-driven methods for SST time-series predictionshow promising results. However, they are limited by neglecting complexinteractions between SST and other ocean environmental factors, such as airtemperature and wind speed. This paper uses multi-factor time series SSTdata to propose a sequence-to-sequence network with two-module attention(TMA-Seq2seq) for long-term time series SST prediction. Specifically, TMASeq2seq is an LSTM-based encoder-decoder architecture facilitated by factorand temporal-attention modules and the input of multi-factor time series. Ittakes six-factor time series as the input, namely air temperature, air pressure,wind speed, wind direction, SST, and SST anomaly (SSTA). A factor attentionmodule is first designed to adaptively learn the effect of different factors onSST, followed by an encoder to extract factor-attention weighted features asfeature representations. And then, a temporal attention module is designedto adaptively select the hidden states of the encoder across all time steps tolearn more robust temporal relationships. The decoder follows the temporalattention module to decode the feature vector concatenated from the weightedfeatures and original input feature. Finally, we use a fully-connect layer tomap the feature into prediction results. With the two attention modules, ourmodel effectively improves the prediction accuracy of SST since it can notonly extract relevant factor features but also boost the long-term *** experiments on the datasets of China Coastal Sites (CCS) demonstrate that our proposed model outperforms other methods, reaching 98.29%in prediction accuracy (PACC) and 0.34 in root mean square error (RMSE).Moreover, SST prediction experiments in China’s East, South,

关键词： Sea surface temperature multi-factor attention long short-term memory

Incentive-driven Federated Learning in Mobile Edge Networks

学校读者我要写书评

暂无评论

Incentive-driven Federated Learning in Mobile Edge Networks

International Conference on Distributed Computing Systems Workshop

作者： Yanlang Zheng Huan Zhou Liang Zhao Shouzhi Xu Victor C. M. Leung Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering College of Computer and Information Technology China Three Gorges University Yichang China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

Federated Learning (FL) is proposed as a privacy-preserving distributed learning methodology that can better protect the privacy and reduce communication costs. To stimulate sufficient User Equipments (UEs) to participate in FL, proper incentives need to be designed for FL. Existing incentive mechanisms do not jointly consider UE selection and local learning accuracy optimization to reduce the training expenditure. This paper designs a reverse auction-based incentive mechanism for FL to minimize the training expenditure of Base Station (BS). To this end, we first propose a Greedy Winner Determination (GWD) algorithm to select UEs with the minimum bidding prices. Then, we incorporate the Particle Swarm Optimization (PSO)-based local learning accuracy optimization into UE selection to further reduce the training expenditure of BS. In addition, we design a Vickrey Clarke Groves (VCG)-based payment rule to determine the payment to each participating UE. The simulation experiments show that our proposed PSO with Winner Determination (PSOWD) algorithm is superior to other existing methods in different scenarios.

关键词：